Alex Cowperthwaite
Technical Director of Research and Development
Cyber and Data Resilience
Toronto
Webinar Replay – AI Security Testing: Prompt Injection Everywhere
September 25, 2024 | (Online)
Kroll offers a glimpse into the security vulnerabilities faced by businesses adopting Artificial Intelligence (AI), Machine Learning (ML) and Large Language Model (LLM) following eight months of LLM penetration testing.
Kroll’s LLM penetration testing has seen it analyze data sets of OpenAI models, non-public models and RAG systems. It has used this to produce an anonymized dataset that catalogs vulnerabilities from all LLM engagements.
Kroll has found a worrying prevalence of prompt injection attacks in the LLM cases it has investigated and shares its findings in this briefing.
Key Takeaways
- Introduction: What is a prompt injection security attack?
- Research Findings: 92% of assessments with LLM findings had prompt injection, 38% of assessments with LLM findings had multiple prompt injection vulnerabilities
- Case Studies: Tales from the trenches of prompt injection attacks
- Impact: Why is prompt injection so prevalent?
- Mitigation: Ways to mitigate the risk of prompt injection attacks
Dive Deeper into Kroll’s Cyber Risk Solutions
Get a better understanding of the breadth of Kroll’s cyber risk services. Download below for more information:
Download the Latest Research from Kroll
Grab a copy of the latest reports and insights below and stop by to discuss with our experts. Click to download:
- Q2 2024 Cyber Threat Landscape Report
- Q1 2024 Cyber Threat Landscape Report
- The State of Cyber Defense: Diagnosing Cyber Threats in Healthcare
- Data Breach Outlook 2023
- Managed Detection and Response (MDR) Buyer’s Guide
- Microsoft Threat Detection and Response: Five Key Pitfalls
- The State of Cyber Defense 2023: Detection and Response Maturity Model
Connect With Us
Cyber and Data Resilience
Incident response, digital forensics, breach notification, security strategy, managed security services, discovery solutions, security transformation.
AI Security Testing Services
AI is a rapidly evolving field and Kroll is focused on advancing the AI security testing approach for large language models (LLM) and, more broadly, AI and ML.
Red Team Security Services
Red team security services from Kroll go beyond traditional penetration testing, leveraging our frontline threat intelligence and the adversarial mindset used by threat actors to push the limits of your information security controls.
Penetration Testing Services
Validate your cyber defenses against real-world threats. Kroll’s world-class penetration testing services bring together front-line threat intelligence, thousands of hours of cyber security assessments completed each year and a team of certified cyber experts — the foundation for our sophisticated and scalable approach.
Cloud Security Services
Kroll’s multi-layered approach to cloud security consulting services merges our industry-leading team of AWS and Azure-certified architects, cloud security experts and unrivalled incident expertise.
Cyber Risk Retainer
Kroll delivers more than a typical incident response retainer—secure a true cyber risk retainer with elite digital forensics and incident response capabilities and maximum flexibility for proactive and notification services.
Kroll Responder MDR
Stop cyberattacks. Kroll Responder managed detection and response is fueled by seasoned IR experts and frontline threat intelligence to deliver unrivaled response.
Cyber Threat Intelligence
Threat intelligence are fueled by frontline incident response intel and elite analysts to effectively hunt and respond to threats.
Kroll is headquartered in New York with offices around the world.
One World Trade Center
285 Fulton Street, 31st Floor
New York NY 10007
Sign up to receive periodic news, reports, and invitations from Kroll.
Our privacy policy describes how your data will be processed.
© 2024 Kroll, LLC. All rights reserved.
Kroll is not affiliated with Kroll Bond Rating Agency,
Kroll OnTrack Inc. or their affiliated businesses. Read more.